Classification using Hierarchical Naïve Bayes models
Machine Learning
Classification-based objective functions
Machine Learning
Hi-index | 0.00 |
In this study, we propose a novel neural net-based classifier called improved Hybrid Wavelet Neural Networks (iHWNN). iHWNN makes good use of the characteristics of Wavelet Neural Networks (WNN) and Back Propagation Neural Networks (BPN), so that it inherits WNN's capability in learning efficiency and BPN's applicability in handling problems of large dimensions. To show the advantages of the developed algorithm, we compare its performance with those from existing classifier systems on several applications. Comparable results are achieved over several datasets from the UCI Machine Learning, with an average increase in accuracy from 91.69% for classification-based objective functions training to 94.17% using optimized iHWNN networks.